Search Results for author:
Found 9 papers, 6 papers with code
ConvTextTM: An Explainable Convolutional Tsetlin Machine Framework for Text Classification
Recent advancements in natural language processing (NLP) have reshaped the industry, with powerful language models such as GPT-3 achieving superhuman performance on various tasks.
Ranked #1 on
Fake News Detection
on PolitiFact
Contracting Tsetlin Machine with Absorbing Automata
In brief, the TA of each clause literal has both an absorbing Exclude- and an absorbing Include state, making the learning scheme absorbing instead of ergodic.
Verifying Properties of Tsetlin Machines
Then, we show the correctness of our encoding and provide results for the properties: adversarial robustness, equivalence, and similarity of TsMs.
Building Concise Logical Patterns by Constraining Tsetlin Machine Clause Size
This paper introduces a novel variant of TM learning - Clause Size Constrained TMs (CSC-TMs) - where one can set a soft constraint on the clause size.
Tsetlin Machine Embedding: Representing Words Using Logical Expressions
We also visualize word clusters in vector space, demonstrating how our logical embedding co-locate similar words.
Explainable Tsetlin Machine framework for fake news detection with credibility score assessment
The proliferation of fake news, i. e., news intentionally spread for misinformation, poses a threat to individuals and society.
Word-level Human Interpretable Scoring Mechanism for Novel Text Detection Using Tsetlin Machines
Our approach encodes a description of the novel documents using the linguistic patterns captured by TM clauses.
Measuring the Novelty of Natural Language Text Using the Conjunctive Clauses of a Tsetlin Machine Text Classifier
The mechanism uses the conjunctive clauses of the TM to measure to what degree a text matches the classes covered by the training data.
Massively Parallel and Asynchronous Tsetlin Machine Architecture Supporting Almost Constant-Time Scaling
We evaluated the proposed parallelization across diverse learning tasks and it turns out that our decentralized TM learning algorithm copes well with working on outdated data, resulting in no significant loss in learning accuracy.
